Abstract: Broadly speaking, embodiments of the present techniques provide methods and systems for robot navigation in an unknown environment. In particular, the present techniques provide a navigation system comprising a navigating device and a sensor network comprising a plurality of static sensors. The sensor network is trained to predict a direction to a target object, and the navigating device is trained to reach the target object as efficiently as possible using information obtained from the sensor network.

Abstract: The present invention discloses an intelligent lubricant spraying system for a high-speed gear transmission, which comprises an oil tank, an oil pump, a driving gear, a driven gear, and a spray nozzle. One end of the oil pump is communicated with the oil tank through the first oil inlet pipe. The driving gear is rotatably supported above the oil tank. The driven gear is meshed with the driving gear and is rotatably supported above the oil tank. The spray nozzle is communicated with the other end of the oil tank through the second oil inlet pipe. The spray nozzle is supported between the driving gear and the driven gear and is used for spraying a lubricant in the oil tank into a meshing part of the driving gear and the driven gear.

Abstract: Systems and methods providing adaptive path planning techniques utilizing localized learning with global planning are described. The adaptive path planning of embodiments provides global guidance and performs local planning based on localized learning, wherein the global guidance provides a planned path through the dynamic environment from a start location to a selected destination while the local planning provides for dynamic interaction within the environment in reaching the destination, such as in response to obstacles entering the planned path. Global guidance may combine an initial global path with history information for providing a global path configured to avoid points of frequent traffic conflicts. Local planning may utilize localized deep reinforcement learning to direct interactions of an automated vehicle traversing the global path in a dynamic environment, such as in response to obstacles entering the global path.

Abstract: According to the present invention, firstly multiple reference parameter values of each color sample in a color chart are set, or a photograph and a measurement are performed on a standard color chart or a user-defined color chart in a certain standard lighting environment, multiple reference parameter values, SPD (?)×R (?) and brightness of each color sample are obtained. Then the SPD (?)×R (?) and the brightness of each color sample are reproduced by using a spectral tunable lighting source. Then each reproduced color sample is photographed by using the camera under the same settings to obtain multiple reproduced parameter values of each color sample. The two groups of parameter values are compared and a color calibration model is established. Finally color calibration of each batch of camera modules is implemented without the helping of a color chart and standard lighting environment.

Abstract: According to the present invention, firstly multiple reference parameter values of each color sample in a color chart are set, or a photograph and a measurement are performed on a standard color chart or a user-defined color chart in a certain standard lighting environment, multiple reference parameter values, SPD (?)×R (?) and brightness of each color sample are obtained. Then the SPD (?)×R (?) and the brightness of each color sample are reproduced by using a spectral tunable lighting source. Then each reproduced color sample is photographed by using the camera under the same settings to obtain multiple reproduced parameter values of each color sample. The two groups of parameter values are compared and a color calibration model is established. Finally color calibration of each batch of camera modules is implemented without the helping of a color chart and standard lighting environment.